© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212401
    Prev
    Next
    INDEX
    Explanations

    Bill of Lading

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptive noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     auff
    0.52
     algéb
    0.50
    峦
    0.49
     اليمن
    0.48
     أل
    0.48
     interrump
    0.47
     offensively
    0.46
     entregar
    0.45
    蛊
    0.45
     exécut
    0.45
    POSITIVE LOGITS
     Forms
    0.49
    onan
    0.47
    публи
    0.47
    scribed
    0.47
     forms
    0.44
    ாதி
    0.44
    ine
    0.44
     እንዲሁ
    0.43
     informing
    0.43
     பகுதியில்
    0.42
    Activations Density 0.000%

    No Known Activations